spinochenza/abliteration-harmful-enriched download history

spinochenza/abliteration-harmful-enriched is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 71 times (29 in the last 7 days), and 144 times in total. It ranks #145,173 among datasets by monthly downloads.

abliteration-harmful-enriched Enriched harmful prompt dataset for abliteration (refusal direction identification). 7356 prompts across 33 categories, designed to provide broad coverage of the refusal subspace for more accurate direction estimation. Used to produce: Bahushruth/Qwen3.6

Open spinochenza/abliteration-harmful-enriched on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.